TY - JOUR
T1 - Data-driven topology design using a deep generative model
AU - Yamasaki, Shintaro
AU - Yaji, Kentaro
AU - Fujita, Kikuo
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/9
Y1 - 2021/9
N2 - In this paper, we propose a sensitivity-free and multi-objective structural design methodology called data-driven topology design. It is schemed to obtain high-performance material distributions from initially given material distributions in a given design domain. Its basic idea is to iterate the following processes: (i) selecting material distributions from a dataset of material distributions according to eliteness, (ii) generating new material distributions using a deep generative model trained with the selected elite material distributions, and (iii) merging the generated material distributions with the dataset. Because of the nature of a deep generative model, the generated material distributions are diverse and inherit features of the training data, that is, the elite material distributions. Therefore, it is expected that some of the generated material distributions are superior to the current elite material distributions, and by merging the generated material distributions with the dataset, the performances of the newly selected elite material distributions are improved. The performances are further improved by iterating the above processes. The usefulness of data-driven topology design is demonstrated through numerical examples.
AB - In this paper, we propose a sensitivity-free and multi-objective structural design methodology called data-driven topology design. It is schemed to obtain high-performance material distributions from initially given material distributions in a given design domain. Its basic idea is to iterate the following processes: (i) selecting material distributions from a dataset of material distributions according to eliteness, (ii) generating new material distributions using a deep generative model trained with the selected elite material distributions, and (iii) merging the generated material distributions with the dataset. Because of the nature of a deep generative model, the generated material distributions are diverse and inherit features of the training data, that is, the elite material distributions. Therefore, it is expected that some of the generated material distributions are superior to the current elite material distributions, and by merging the generated material distributions with the dataset, the performances of the newly selected elite material distributions are improved. The performances are further improved by iterating the above processes. The usefulness of data-driven topology design is demonstrated through numerical examples.
KW - Data-driven design
KW - Deep generative model
KW - Estimation of distribution algorithm
KW - Multi-objective methodology
KW - Sensitivity-free methodology
KW - Topology optimization
UR - http://www.scopus.com/inward/record.url?scp=85114309411&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114309411&partnerID=8YFLogxK
U2 - 10.1007/s00158-021-02926-y
DO - 10.1007/s00158-021-02926-y
M3 - Article
AN - SCOPUS:85114309411
SN - 1615-147X
VL - 64
SP - 1401
EP - 1420
JO - Structural and Multidisciplinary Optimization
JF - Structural and Multidisciplinary Optimization
IS - 3
ER -